VIDEO
HIGHLIGHT
Log InSign up
Análisis de la relación entre dos variables cualitativas: Test Chi cuadrado. Módulo 4
SummaryTranscriptChat

Análisis de la relación entre dos variables cualitativas: Test Chi cuadrado. Módulo 4

New Section

In this section, the speaker introduces the topic of analyzing the relationship between two qualitative variables using the chi-square test. An example involving treatments and patient responses is presented to illustrate the concept.

Introduction to Analyzing Qualitative Variables

  • The data example is drawn from a biostatistics book by Martín Andrés and Luna del Castillo, focusing on four treatments and three response levels.
  • The table of data represents different treatments' outcomes for patients, emphasizing how this two-way table is known as a contingency table in practice.
  • The speaker discusses adapting the scenario to various fields beyond medical treatments, such as political opinions or other categorical variables.

Exploring Hypotheses and Calculating Marginal Frequencies

This part delves into formulating hypotheses regarding variable independence and calculating marginal frequencies based on treatment outcomes.

Formulating Hypotheses and Marginal Frequencies

  • Emphasizes setting up theoretical hypotheses (H0) assuming variable independence until proven otherwise with data evidence.
  • Discusses deciding between null hypothesis (independence) and alternative hypothesis (relationship) based on treatment outcome data analysis.
  • Illustrates how comparing total improvements across treatments requires considering sample sizes to avoid premature conclusions about treatment effectiveness.

Understanding Marginal Frequencies Calculation

This segment focuses on calculating marginal frequencies for rows and columns in contingency tables to aid in statistical analysis.

Calculating Marginal Frequencies

  • Demonstrates calculating row marginal frequencies by summing corresponding treatment outcomes for statistical analysis.
  • Expands on computing column marginal totals similarly to enhance understanding of overall treatment effects.

New Section

In this section, the speaker discusses the calculation of expected frequencies in a data analysis context.

Calculating Expected Frequencies

  • The expected frequency in a specific position of a table can be calculated by multiplying the total of the corresponding row by the total of the corresponding column and dividing it by the overall total.
  • After calculating theoretical frequencies based on independence assumptions, discrepancies between observed and expected frequencies are evaluated to assess data relationships.
  • Specific examples are provided, such as determining the expected value at a position if responses were independent of treatment variables.
  • Calculation involves finding marginal totals for rows and columns to determine expected values, highlighting differences between observed absolute frequencies and theoretical non-integer values.
  • The process extends to all cases within the dataset, with each cell's expected frequency being computed based on row and column totals divided by the overall total.

New Section

This segment delves into further calculations related to expected frequencies in statistical analysis.

Further Calculations on Expected Frequencies

  • Detailed explanations are given on how various expected frequencies are computed using row and column marginal totals divided by the overall total.
  • The discussion progresses to measuring discrepancies between observed and theoretical frequencies through squared differences divided by corresponding expected frequencies for all cells in the table.
  • Instead of directly subtracting observed from expected values, squared differences normalized by expected values are summed across all cells following statistical principles.

New Section

In this section, the speaker discusses experimental values and their comparison with theoretical values using a specific table.

Experimental vs. Theoretical Values

  • The experimental value obtained is 13.87.
  • Degrees of freedom are calculated based on the dimensions of the table.
  • The theoretical value for a 5% risk level with 6 degrees of freedom is 12.59.
  • A comparison reveals that the experimental value (13.87) exceeds the theoretical value (12.59).

New Section

This part focuses on drawing conclusions based on the relationship between treatment and response in data analysis.

Drawing Conclusions

  • The response is concluded to be dependent on treatment due to data analysis insights.
  • Utilizing formulas and calculations aids in determining significance levels.
  • Low expected frequencies can impact statistical outcomes significantly.
Video description

Titulo curso: Estadística para investigadores, todo lo que siempre quiso saber y no se atrevió a preguntar Cursos Online Masivos y Abiertos de la Universidad de Salamanca. Breve info: Si alguna vez has tenido problemas con la estadística, este curso está hecho para ti. Es ideal para investigadores y alumnos que se encuentran cursando trabajos fin de grado, trabajos fin de máster o realizando la tesis y que quieren realizar un análisis cuantitativo en sus estudios. Partimos sin nivel de conocimientos previos y está dirigido a todo el mundo que tenga inquietudes en la interpretación de datos estadísticos. Además, es ideal para recordar y actualizar los conocimientos que ya tiene sobre estadística básica, proporcionándole un buena base para su investigación, de una manera muy sencilla de comprender. Es un curso muy intuitivo, en el que hacemos énfasis en la utilidad que le proporciona al alumno de cualquiera de las disciplinas del conocimiento, ya sean para estudios en ciencias sociales o ciencias de la salud, donde ponemos de manifiesto las ventajas y las limitaciones de cada una de las técnicas. Mas info en: http://diarium.usal.es/mooc/estadistica-para-investigadores/ y en twitter https://twitter.com/USALMOOC